ANN-Based Operational Planning of Power Systems

1
ANN-Based Operational Planning of Power Systems

• M. E. El-Hawary
• Dalhousie University
• Halifax, Nova Scotia, Canada

7th Annual IEEE Technical Exchange Meeting, April
18-19, 2000 Saudi Arabia Section, and KFUPM
2
What am I to do?

• I suspect that the audience includes people who
  are not power-oriented.
• Offer a generic presentation.
• Power examples are easily related to other areas.

3
ANN Basics

• Emulate behavior of systems of neurons.
• A neuron nudges its neighbor in proportion to
  its stimulus.
• The strength of the nudge is a weight.
• Sum the weighted stimuli.
• Scale using sigmoidal function

4
Basic Neuron Model
W1j
x1
Neuron i
W2j
vi
x2
W3i
x3
5
Sigmoid Function

• Use plain sigmoid formula

Alternatively
6
Three Layer Back Propagation Network
y1
yn
yi
W1q
q
v1q
xm
x1
xj
7
The Process

• Learning based on training patterns.
• Initialize weights.
• Present training patterns and successively update
  weights.
• Updates initially based on steepest decscent.
• Current trend is to use an appropriate NL descent
  method.
• Iterate on weights until no further improvements.

8
Hopfield Network

• Each neuron contains two op amps.
• The output of neuron j is connected to input of
  neuron i through a conductance Wij

9
HNN Formulae
Energy Function
Neuron Dynamics
10
General Idea

• Take NLP problem

11
Mapping
Ignore inequality constraints Relate variable X
to neuron output V
The energy function will contain the m equality
constraint terms in addition to the objective.
12
Sample Operational Planning Problems

• Unit Commitment
• Economic Dispatch
• Environmental Dispatch
• Dynamic Dispatch
• Maintenance Scheduling
• Expansion Planning

13
Unit Commitment

• Given a set of available generating units and a
  load profile over an optimization horizon.
• Find the on/off sequence for all units for
  optimal economy.
• Recognize start up and running costs.

14
Constraints

• Minimum up and down times
• Ramping limits.
• Power balance

15
Economic Dispatch

• Find optimal combination of power generation to
  minimize total fuel cost.
• We know the cost model parameters

16
Constraints

• Meet power balance equation including losses.
• L represents the losses and D is the demand
• Losses are assumed constant

17

• Satisfy upper and lower limits on power
  generations

18
NN Aided Unit Commitment
19
Back Propagation Assisted Unit Commitment
20
Approach A-1Multi-stage ApproachANN-Priority
List-ANN Refined

• Ouyang and Shahidehpour (May 1992)
• Three stage process
• Stage 1 ANN Prescheduling
• Stage 2 Priority based heuristics.
• Stage 3 ANN Refinement

21
Stage 1ANN Prescheduler

• Obtain a set of load profiles corresponding
  commitment schedules.
• Cover basic categories of days.
• Train ANN.
• Feed forecast load to trained ANN.
• Output of ANN is a preschedule.

22
Pre-scheduling (cont.)

• Input is 24 x N matrix.
• N is load demand segments.
• Each matrix element is related to a neuron in the
  input layer.
• Each training load pattern corresponds to an
  index number in the output layer

23
Pre-scheduling (cont.)

• Recommends 50 to 100 training patterns.
• NN prescheduling saves time and offers better
  matching.

24
Stage 2Sub-optimal Schedule

• Consider outcome of prescheduling.
• Use priority list.
• Check minimum up and down times.
• Examine on/off status of units and modify.

25
Stage 3ANN Schedule Refiner

• Trained using pairs of sub-optimal solutions as
  input and optimal solution as output.
• NN generalizes the refinement rule.
• Used three different techniques.

26
Training Pattern Generation(Cont.)

• Operator generated better unit commitment
  solutions.
• Base units are not involved in the refinement
  process.

27
Hopfield Implementaions

• Usually BP Nets are good at pattern recognition.
• For optimization problems, the Hopfield network
  has been shown to be more effective.
• By way of example, we show the application to
  economic dispatch.

28
Mapping ED to HNN

• Write the energy function as

29

• Finds mappings as

30
Improvements
Choose large A Use momentum term
31
What Else?

• Virtually every area involving prediction or
  optimization has been treated using ANN.
• Examples include hand movement animation.
• Computer communication network congestion
  management.
• Computer communication network routing

32
Thanks

• I hope that we learned something together.
• Thanks to all of you, and specially Dr. Samir
  Al-Baiyat and the Organizing Committee